Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    党组
    -0.08
     sued
    -0.07
    河边
    -0.07
    itas
    -0.07
    stands
    -0.07
    unsch
    -0.07
     INA
    -0.07
    itat
    -0.07
    .reporting
    -0.07
    عامل
    -0.06
    POSITIVE LOGITS
    .mount
    0.08
    ذكر
    0.07
     cart
    0.07
     proved
    0.07
    .emplace
    0.07
     separators
    0.06
    !"↵↵
    0.06
    .thread
    0.06
     bibli
    0.06
    不存在
    0.06
    Act Density 0.357%

    No Known Activations